...if statistics are your field and there is simply no way, in your model, to account for psychological differences which could explain the statistics, perhaps it is better not to claim to be able to explain the cause of the statistics better than a psychologist?
-
-
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
I was really shocked by the bizarreness of that argument. It seems he's saying if event A predates event B, then A causes B, so you cannot control for B when considering some outcome C.
-
Kareem, that is true. http://scunning.com/cunningham_mixtape.pdf … page 74. This is a standard statistical result.
-
Then we'd have a problem with this method. If the wage gap were caused by men and women happily making different choices, there'd be absolutely no way to show this.
-
Yes. That's what we're telling you. When you and folks like Peterson say "oh, it dissapointed with occupational controls" all you are demonstrating is that you haven't thought carefully about the issue. Causal inference is *hard*, especially about stuff like nature/nurture.
-
If you want to have a conversation about this, talk to me civilly and in good faith without sneering condescension. Otherwise I will just mute you and discuss it with someone who can manage to disagree with me without vitriol.
-
I'm not talking with vitriol. I am trying to explain to you that you are making a statistical error. Lots of people are unfamiliar with statistical methods!
-
Statistics will tell us what is. I am concerned with why that is. There is no disagreement that a gap exists. You are telling me statistics cannot tell us why it does. Therefore, they are of no use to the ethical discussion.
-
Statistics can tell us a lot! See the reivews I sent you! But you can't put choice variables on the right hand side.
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.